AI Paper Atlas

Research map / Image generation / Super-resolution

NeurOp-Diff: Continuous Remote Sensing Image Super-Resolution via Neural Operator Diffusion

Zihao Xu, Yuzhi Tang, Bowen Xu, Qingquan Li

ICCV 2025 · Image generation › Super-resolution · approach: Efficient lightweight super-resolution · 8 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
condition diffusion on neural-operator-encoded LR features instead of bicubic-upsampled LR (ablation)NeurOp-Diff · UCMerced 4x SRPSNR: 27.15 -> 28.14Improved
condition diffusion on neural-operator-encoded LR features instead of bicubic-upsampled LR (ablation)NeurOp-Diff · UCMerced 4x SRSSIM: 0.7587 -> 0.7761Improved
condition on neural-operator features instead of EDSR-encoded LR features (ablation)NeurOp-Diff · UCMerced 4x SRPSNR: 27.42 -> 28.14Improved
condition on neural-operator features instead of EDSR-encoded LR features (ablation)NeurOp-Diff · UCMerced 4x SRSSIM: 0.7602 -> 0.7761Improved
NeurOp-Diff vs SR3 baseline at 8xSR3 · UCMerced 8x SRPSNR: 23.12 -> 24.51Improved
NeurOp-Diff vs best generative baseline TCDM at 4xTCDM · AID 4x SRPSNR: 27.53 -> 27.57No clear effect
NeurOp-Diff vs TCDM at 4xTCDM · UCMerced 4x SRPSNR: 27.83 -> 28.14Improved
NeurOp-Diff vs IDM in inference time at T=50IDM · Inference time per imageseconds: 1.79 -> 1.52Improved
NeurOp-Diff vs SR3 inference time at T=100SR3 · Inference time per imageseconds: 3.23 -> 2.61Improved
NeurOp-Diff vs regression SRNO at 4xSRNO · UCMerced 4x SRPSNR: 29.21 -> 28.14Hurt
NeurOp-Diff vs regression SRNO at 4xSRNO · UCMerced 4x SRLPIPS: 0.164 -> 0.136Improved
NeurOp-Diff vs SRNO at out-of-distribution 10xSRNO · UCMerced continuous SR 10xSSIM: 0.592 -> 0.633Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy